diff_of_means ratio_of_sd amplitude_ratio_of_means maximum_error sign_error qqplot_mae acf_mae extremogram_mae
lstm.cesm2.ssp370 0.01% 0.906 0.945 0.227 0.102 0.554 0.233 0.100
lstm.mri_esm2_0.ssp434 0.02% 0.921 0.962 0.234 0.105 0.472 0.212 0.092
lstm.cesm2.ssp585 0.03% 0.907 0.959 0.240 0.100 0.573 0.250 0.109
lstm.cesm2.ssp245 0.04% 0.911 0.949 0.233 0.100 0.571 0.233 0.089
lstm.mri_esm2_0.ssp245 0.06% 0.926 0.962 0.238 0.105 0.532 0.212 0.104
lstm.mri_esm2_0.ssp370 0.06% 0.925 0.974 0.251 0.104 0.498 0.228 0.097
lstm.ec_earth3.ssp434 0.07% 0.909 0.953 0.241 0.105 0.718 0.242 0.132
nv.mri_esm2_0.ssp370 -0.13% 1.109 0.961 0.114 0.048 0.631 0.068 0.034
xgboost.mri_esm2_0.ssp370 -0.16% 1.050 0.842 0.380 0.069 0.519 0.106 0.028
nv.mri_esm2_0.ssp434 -0.17% 1.155 0.963 0.108 0.047 0.878 0.085 0.053
xgboost.mri_esm2_0.ssp434 -0.19% 1.088 0.855 0.381 0.069 0.689 0.115 0.025
nv.ec_earth3.ssp434 -0.27% 1.019 0.946 0.163 0.048 0.775 0.065 0.021
xgboost.ec_earth3.ssp434 -0.28% 0.960 0.726 0.342 0.072 0.842 0.136 0.031
cnn.mri_esm2_0.ssp434 0.31% 1.152 1.193 0.437 0.237 1.400 0.151 0.154
cnn.cesm2.ssp370 0.31% 1.114 1.185 0.418 0.233 1.253 0.191 0.164
cnn.cesm2.ssp245 0.31% 1.108 1.186 0.424 0.231 1.292 0.182 0.161
cnn.ec_earth3.ssp434 0.31% 1.160 1.191 0.392 0.234 1.502 0.161 0.209
cnn.mri_esm2_0.ssp370 0.31% 1.172 1.204 0.446 0.243 1.448 0.155 0.167
cnn.mri_esm2_0.ssp245 0.32% 1.174 1.196 0.428 0.239 1.503 0.153 0.167
nv.mri_esm2_0.ssp245 -0.32% 1.153 0.962 0.112 0.048 1.031 0.086 0.100
xgboost.mri_esm2_0.ssp245 -0.33% 1.081 0.873 0.381 0.068 0.962 0.108 0.025
cnn.cesm2.ssp585 0.36% 1.094 1.190 0.419 0.229 1.333 0.208 0.161
nv.cesm2.ssp585 -0.44% 0.995 0.958 0.111 0.048 1.294 0.031 0.016
xgboost.cesm2.ssp585 -0.47% 0.940 0.808 0.365 0.068 1.381 0.082 0.018
nv.cesm2.ssp245 -0.51% 0.997 0.956 0.126 0.048 1.482 0.034 0.041
xgboost.cesm2.ssp245 -0.52% 0.939 0.813 0.375 0.070 1.534 0.081 0.025
nv.cesm2.ssp370 -0.57% 0.967 0.959 0.127 0.047 1.651 0.019 0.017
xgboost.cesm2.ssp370 -0.59% 0.911 0.805 0.363 0.068 1.734 0.072 0.024

Time series of the first days

How Often Peaks Hit Hourly

QQ Plot

Distribution of the undownscaled value on days with estimated extremes values.

On the x-axis we have the daily mean (standardized). It says Undownscaled value, but is the daily mean after the downscaling. A good idea is to plot the original undownscaled value.

The purpose of this plot is to illustrate the distribution of P(undownscaled value | we predicted an extreme). This is useful because it reveals how much information we can recover concerning extreme events. If the distribution is skewed to the right, it suggests that we’re predicting extreme values only when extreme values have already occurred. Conversely, if the lower tail of the distribution resembles the reanalysis data, it indicates that we can capture short-duration extremes (e.g., brief periods of heavy rainfall, such as an intense downpour lasting an hour before stopping).

Autocorrelogram

Extremogram